This paper describes a solution procedure which allows for standard linear methods to
analyze the characteristic equilibrium interaction between the stochastic environment and
non-linearities in dynamic rational expectations models. The solution procedure consists
of two steps: The first step is to approximate the original system of stochastic equilibrium conditions by a k-order Taylor series expansion in the exogenous disturbances about
the deterministic model. The result is an approximated system of equilibrium conditions
which is non-stochastic, nonlinear in the endogenous variables, but which is now linear
in the first k moments of the exogenous disturbances. The second step of the solution
procedure is then to use standard (linear) methods to compute the solution to the new
equilibrium system as the approximation to the solution of the original system. The important implication of the solution procedure is that the steady state of the approximated
equilibrium system and its linearized solution process of the endogenous variables fully
capture the equilibrium interaction of the stochastic environment and the non-linearities
of the model up the first k moments.